# GS2Mesh: Surface Reconstruction from Gaussian Splatting via Novel Stereo Views

arXiv: https://arxiv.org/abs/2404.01810 · HTML: https://mlsanity.com/paper/2404.01810/

## Key facts

- Cited by 67 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 58 references that are in the map.
- First posted on arXiv 2 Apr 2024.

## Builds on (most cited first, 30 of 43)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021)
- [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://mlsanity.com/paper/2106.10689/) (2021)
- [2D Gaussian Splatting for Geometrically Accurate Radiance Fields](https://mlsanity.com/paper/2403.17888/) (2024)
- [Volume Rendering of Neural Implicit Surfaces](https://mlsanity.com/paper/2106.12052/) (2021)
- [MVSNet: Depth Inference for Unstructured Multi-view Stereo](https://mlsanity.com/paper/1804.02505/) (2018)
- [Mip-Splatting: Alias-free 3D Gaussian Splatting](https://mlsanity.com/paper/2311.16493/) (2023)
- [SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering](https://mlsanity.com/paper/2311.12775/) (2023)
- [Pyramid Stereo Matching Network](https://mlsanity.com/paper/1803.08669/) (2018)
- [Neuralangelo: High-Fidelity Neural Surface Reconstruction](https://mlsanity.com/paper/2306.03092/) (2023)
- [Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching](https://mlsanity.com/paper/1912.06378/) (2019)
- [End-to-End Learning of Geometry and Context for Deep Stereo Regression](https://mlsanity.com/paper/1703.04309/) (2017)
- [RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching](https://mlsanity.com/paper/2109.07547/) (2021)
- [3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions](https://mlsanity.com/paper/1603.08182/) (2016)
- [GA-Net: Guided Aggregation Net for End-to-end Stereo Matching](https://mlsanity.com/paper/1904.06587/) (2019)
- [A Survey on 3D Gaussian Splatting](https://mlsanity.com/paper/2401.03890/) (2024)
- [BakedSDF: Meshing Neural SDFs for Real-Time View Synthesis](https://mlsanity.com/paper/2302.14859/) (2023)
- [PatchmatchNet: Learned Multi-View Patchmatch Stereo](https://mlsanity.com/paper/2012.01411/) (2020)
- [GaussianPro: 3D Gaussian Splatting with Progressive Propagation](https://mlsanity.com/paper/2402.14650/) (2024)
- [COLMAP-Free 3D Gaussian Splatting](https://mlsanity.com/paper/2312.07504/) (2023)
- [Iterative Geometry Encoding Volume for Stereo Matching](https://mlsanity.com/paper/2303.06615/) (2023)
- [Segment Any 3D Gaussians](https://mlsanity.com/paper/2312.00860/) (2023)
- [Cost Volume Pyramid Based Depth Inference for Multi-View Stereo](https://mlsanity.com/paper/1912.08329/) (2019)
- [CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching](https://mlsanity.com/paper/2104.04314/) (2021)
- [Multi-Scale 3D Gaussian Splatting for Anti-Aliased Rendering](https://mlsanity.com/paper/2311.17089/) (2023)
- [NeuSG: Neural Implicit Surface Reconstruction with 3D Gaussian Splatting Guidance](https://mlsanity.com/paper/2312.00846/) (2023)
- [Improving neural implicit surfaces geometry with patch warping](https://mlsanity.com/paper/2112.09648/) (2021)

## Built on by (most cited first, 30 of 67)

- [CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale Scenes](https://mlsanity.com/paper/2411.00771/) (2024)
- [Neural Signed Distance Function Inference through Splatting 3D Gaussians Pulled on Zero-Level Set](https://mlsanity.com/paper/2410.14189/) (2024)
- [Binocular-Guided 3D Gaussian Splatting with View Consistency for Sparse View Synthesis](https://mlsanity.com/paper/2410.18822/) (2024)
- [Vid2Sim: Realistic and Interactive Simulation from Video for Urban Navigation](https://mlsanity.com/paper/2501.06693/) (2025)
- [Trim 3D Gaussian Splatting for Accurate Geometry Representation](https://mlsanity.com/paper/2406.07499/) (2024)
- [MAtCha Gaussians: Atlas of Charts for High-Quality Geometry and Photorealism From Sparse Views](https://mlsanity.com/paper/2412.06767/) (2024)
- [GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction](https://mlsanity.com/paper/2509.18090/) (2025)
- [MVG-Splatting: Multi-View Guided Gaussian Splatting with Adaptive Quantile-Based Geometric Consistency Densification](https://mlsanity.com/paper/2407.11840/) (2024)
- [Self-Ensembling Gaussian Splatting for Few-Shot Novel View Synthesis](https://mlsanity.com/paper/2411.00144/) (2024)
- [Geometry Field Splatting with Gaussian Surfels](https://mlsanity.com/paper/2411.17067/) (2024)
- [GauSTAR: Gaussian Surface Tracking and Reconstruction](https://mlsanity.com/paper/2501.10283/) (2025)
- [Flex3D: Feed-Forward 3D Generation with Flexible Reconstruction Model and Input View Curation](https://mlsanity.com/paper/2410.00890/) (2024)
- [Revisiting Depth Representations for Feed-Forward 3D Gaussian Splatting](https://mlsanity.com/paper/2506.05327/) (2025)
- [EmbodiedSplat: Personalized Real-to-Sim-to-Real Navigation with Gaussian Splats from a Mobile Device](https://mlsanity.com/paper/2509.17430/) (2025)
- [MonoGSDF: Exploring Monocular Geometric Cues for Gaussian Splatting-Guided Implicit Surface Reconstruction](https://mlsanity.com/paper/2411.16898/) (2024)
- [QuickSplat: Fast 3D Surface Reconstruction via Learned Gaussian Initialization](https://mlsanity.com/paper/2505.05591/) (2025)
- [AGS-Mesh: Adaptive Gaussian Splatting and Meshing with Geometric Priors for Indoor Room Reconstruction Using Smartphones](https://mlsanity.com/paper/2411.19271/) (2024)
- [VTGaussian-SLAM: RGBD SLAM for Large Scale Scenes with Splatting View-Tied 3D Gaussians](https://mlsanity.com/paper/2506.02741/) (2025)
- [GSurf: Learning Signed Distance Fields from Splatting Opaque Gaussians for High-quality 3D Reconstruction](https://mlsanity.com/paper/2411.15723/) (2024)
- [VA-GS: Enhancing the Geometric Representation of Gaussian Splatting via View Alignment](https://mlsanity.com/paper/2510.11473/) (2025)
- [Gaussian Building Mesh (GBM): Extract a Building's 3D Mesh with Google Earth and Gaussian Splatting](https://mlsanity.com/paper/2501.00625/) (2024)
- [PG-SAG: Parallel Gaussian Splatting for Fine-Grained Large-Scale Urban Buildings Reconstruction via Semantic-Aware Grouping](https://mlsanity.com/paper/2501.01677/) (2025)
- [Car-GS: Addressing Reflective and Transparent Surface Challenges in 3D Car Reconstruction](https://mlsanity.com/paper/2501.11020/) (2025)
- [Radiance Fields from Photons](https://mlsanity.com/paper/2407.09386/) (2024)
- [TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction](https://mlsanity.com/paper/2605.26115/) (2026)
- [Seeing A 3D World in A Grain of Sand](https://mlsanity.com/paper/2503.00260/) (2025)
- [SVRecon: Sparse Voxel Rasterization for Surface Reconstruction](https://mlsanity.com/paper/2511.17364/) (2025)
- [ExMesh: Explicit Mesh Reconstruction with Topology Adaptation](https://mlsanity.com/paper/2606.07288/) (2026)
- [Sparse2DGS: Sparse-View Surface Reconstruction using 2D Gaussian Splatting with Dense Point Cloud](https://mlsanity.com/paper/2505.19854/) (2025)
- [RayletDF: Raylet Distance Fields for Generalizable 3D Surface Reconstruction from Point Clouds or Gaussians](https://mlsanity.com/paper/2508.09830/) (2025)

## Abstract (arXiv)

Recently, 3D Gaussian Splatting (3DGS) has emerged as an efficient approach for accurately representing scenes. However, despite its superior novel view synthesis capabilities, extracting the geometry of the scene directly from the Gaussian properties remains a challenge, as those are optimized based on a photometric loss. While some concurrent models have tried adding geometric constraints during the Gaussian optimization process, they still produce noisy, unrealistic surfaces. We propose a novel approach for bridging the gap between the noisy 3DGS representation and the smooth 3D mesh representation, by injecting real-world knowledge into the depth extraction process. Instead of extracting the geometry of the scene directly from the Gaussian properties, we instead extract the geometry through a pre-trained stereo-matching model. We render stereo-aligned pairs of images corresponding to the original training poses, feed the pairs into a stereo model to get a depth profile, and finally fuse all of the profiles together to get a single mesh. The resulting reconstruction is smoother, more accurate and shows more intricate details compared to other methods for surface reconstruction from Gaussian Splatting, while only requiring a small overhead on top of the fairly short 3DGS optimization process. We performed extensive testing of the proposed method on in-the-wild scenes, obtained using a smartphone, showcasing its superior reconstruction abilities. Additionally, we tested the method on the Tanks and Temples and DTU benchmarks, achieving state-of-the-art results.